Security audit
Security checks for vulnerabilities and agentic risk
This skill is a prompt-pack builder that writes user-directed persona product files and does not show hidden access, exfiltration, persistence, or destructive behavior.
Install only if you want an agent workflow for creating persona or prompt-pack files. Use a fresh output directory when running the helper script, and note that the packaged artifact appears to reference templates that were not included, which may make the starter script fail until those templates are supplied.
The skill instructs the agent to read bundled references/assets and to run a local script that writes an output folder, but the manifest does not declare any explicit tool scope or file permissions. This creates a least-privilege gap: an agent/runtime may grant broader file read/write access than the skill actually needs, making unintended filesystem access harder to constrain or audit.
This Python file performs file creation and overwrites generated content via mkdir and write_text calls, which is a safety-relevant operation under the code-file warning rule. While the script's purpose is generation and the CLI description mentions an output directory, there is no user-facing warning or notice that multiple files will be created or overwritten in that location.
No suspicious patterns detected.
